Research map / Label-efficient and robust learning / Domain adaptation and generalization
Invariant Models for Causal Transfer Learning
Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner, Jonas Peters
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use invariant-subset prediction instead of pooling the training tasks | Linear regression with gene intervention data · Gene perturbation, non-causal problems (269 cases) | test error | Improved |
| use invariant-subset prediction instead of pooling the training tasks | Linear regression with gene intervention data · Gene perturbation, causal problems (39 cases) | test error | No clear effect |
| use invariant-subset prediction instead of pooling the training tasks | Linear regression · School dataset | test error | No clear effect |
| set acceptance level delta to 0 so all subsets are accepted (ablation) | Invariant subset search (DG) · Synthetic DG, 3 training tasks | test squared error | Hurt |
| use greedy search instead of full search with many predictors | Invariant subset search · Synthetic DG, p=30 | feasibility and runtime: 1.57 -> 0.0396 seconds at p=10 | Improved |
| increase the number of training tasks beyond four | Invariant subset search · Synthetic DG | test squared error | Improved |
Closest papers by meaning
- Anti-causal domain generalization: Leveraging unlabeled data (ICML 2026 · similarity 0.90)
- Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions (NeurIPS 2018 · similarity 0.90)
- Do causal predictors generalize better to new domains? (NeurIPS 2024 · similarity 0.89)
- Invariant and Transportable Representations for Anti-Causal Domain Shifts (NeurIPS 2022 · similarity 0.89)
- Few-shot Domain Adaptation by Causal Mechanism Transfer (ICML 2020 · similarity 0.88)
- Wasserstein Transfer Learning (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
